arXiv：cs.AI· Hai Lu, Yichen Luo, Luping Yu·· 5 小时前
GPT-4o 与 GPT-5 在同行评审中表现如何？来自金融与会计领域的证据
How Well Do LLMs Perform in Peer Review? Evidence from Finance and Accounting
AI 导读
研究用 GPT-4o 评审 2024 年 AFA 和 NBER 金融会议论文，发现模型评分高出一个标准差的论文在随后两年内发表于三大金融期刊的概率高出 44%，且该结果并非源于前视偏差。
正文
Abstract:Referees increasingly use large language models (LLMs), while finance and accounting journals disagree about whether to allow it. We ask which part of a referee's job the models can do. GPT-4o, whose training data end before the 2024 conference season, referees the papers presented at the 2024 AFA and NBER finance meetings, and we compare its verdicts with publication in the top-three finance journals over the next two years. Papers the model scores one standard deviation higher are 44\% more likely to be published, net of author reputation. The result is not driven by look-ahead bias, as the model does not recall the outcomes. The information comes from its judgements of correctness and exposition. Its judgements of originality and significance carry none, and a referee guide that stresses importance does not help. The split between correctness and contribution holds for accounting papers and for a newer model, GPT-5. LLMs can check whether research is right, but not whether it matters. The technical check can go to the model, while the judgement of contribution stays with people.
| Subjects: | General Finance (q-fin.GN); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.18435 [q-fin.GN] |
| (or arXiv:2610.18435v1 [q-fin.GN] for this version) | |
| https://doi.org/10.48550/arXiv.2610.18435 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Luping Yu [view email]
[v1]
Tue, 13 Oct 2026 14:11:35 UTC (46 KB)
来源：arXiv：cs.AI · arxiv.org